We present "The Relightables", a volumetric capture system for photorealistic and high quality relightable full-body performance capture. While significant progress has been made on volumetric capture systems, focusing on 3D geometric reconstruction with high resolution textures, much less work has been done to recover photometric properties needed for relighting. Results from such systems lack high-frequency details and the subject's shading is prebaked into the texture. In contrast, a large body of work has addressed relightable acquisition for image-based approaches, which photograph the subject under a set of basis lighting conditions and recombine the images to show the subject as they would appear in a target lighting environment. However, to date, these approaches have not been adapted for use in the context of a high-resolution volumetric capture system. Our method combines this ability to realistically relight humans for arbitrary environments, with the benefits of free-viewpoint volumetric capture and new levels of geometric accuracy for dynamic performances. Our subjects are recorded inside a custom geodesic sphere outfitted with 331 custom color LED lights, an array of high-resolution cameras, and a set of custom high-resolution depth sensors. Our system innovates in multiple areas: First, we designed a novel active depth sensor to capture 12.4 MP depth maps, which we describe in detail. Second, we show how to design a hybrid geometric and machine learning reconstruction pipeline to process the high resolution input and output a volumetric video. Third, we generate temporally consistent reflectance maps for dynamic performers by leveraging the information contained in two alternating color gradient illumination images acquired at 60Hz. Multiple experiments, comparisons, and applications show that The Relightables significantly improves upon the level of realism in placing volumetrically captured human performances into arbitrary CG scenes.

We present a novel technique to relight images of human faces by learning a model of facial reflectance from a database of 4D reflectance field data of several subjects in a variety of expressions and viewpoints. Using our learned model, a face can be relit in arbitrary illumination environments using only two original images recorded under spherical color gradient illumination. The output of our deep network indicates that the color gradient images contain the information needed to estimate the full 4D reflectance field, including specular reflections and high frequency details. While capturing spherical color gradient illumination still requires a special lighting setup, reduction to just two illumination conditions allows the technique to be applied to dynamic facial performance capture. We show side-by-side comparisons which demonstrate that the proposed system outperforms the state-of-the-art techniques in both realism and speed.

Motivated by augmented and virtual reality applications such as telepresence, there has been a recent focus in real-time performance capture of humans under motion. However, given the real-time constraint, these systems often suffer from artifacts in geometry and texture such as holes and noise in the final rendering, poor lighting, and low-resolution textures. We take the novel approach to augment such real-time performance capture systems with a deep architecture that takes a rendering from an arbitrary viewpoint, and jointly performs completion, super resolution, and denoising of the imagery in real-time. We call this approach neural (re-)rendering , and our live system "LookinGood". Our deep architecture is trained to produce high resolution and high quality images from a coarse rendering in real-time. First, we propose a self-supervised training method that does not require manual ground-truth annotation. We contribute a specialized reconstruction error that uses semantic information to focus on relevant parts of the subject, e.g. the face. We also introduce a salient reweighing scheme of the loss function that is able to discard outliers. We specifically design the system for virtual and augmented reality headsets where the consistency between the left and right eye plays a crucial role in the final user experience. Finally, we generate temporally stable results by explicitly minimizing the difference between two consecutive frames. We tested the proposed system in two different scenarios: one involving a single RGB-D sensor, and upper body reconstruction of an actor, the second consisting of full body 360° capture. Through extensive experimentation, we demonstrate how our system generalizes across unseen sequences and subjects.

We introduce a realtime compression architecture for 4D performance capture that is two orders of magnitude faster than current state-of-the-art techniques, yet achieves comparable visual quality and bitrate. We note how much of the algorithmic complexity in traditional 4D compression arises from the necessity to encode geometry using an explicit model (i.e. a triangle mesh). In contrast, we propose an encoder that leverages an implicit representation (namely a Signed Distance Function) to represent the observed geometry, as well as its changes through time. We demonstrate how SDFs, when defined over a small local region (i.e. a block), admit a low-dimensional embedding due to the innate geometric redundancies in their representation. We then propose an optimization that takes a Truncated SDF (i.e. a TSDF), such as those found in most rigid/non-rigid reconstruction pipelines, and efficiently projects each TSDF block onto the SDF latent space. This results in a collection of low entropy tuples that can be effectively quantized and symbolically encoded. On the decoder side, to avoid the typical artifacts of block-based coding, we also propose a variational optimization that compensates for quantization residuals in order to penalize unsightly discontinuities in the decompressed signal. This optimization is expressed in the SDF latent embedding, and hence can also be performed efficiently. We demonstrate our compression/decompression architecture by realizing, to the best of our knowledge, the first system for streaming a real-time captured 4D performance on consumer-level networks.

For generalized augmented reality to be feasible, the augmenting elements must be visible in varied environments and under rapidly changing, high dynamic range lighting, from bright sunlight to deep shadows. We present a high dynamic range, optical see-through, augmented reality display that dynamically adjusts the brightness of the virtual imagery to match the current brightness of the real scene. Critical components include the spatial brightness sensor array and the positional brightness image intensity matcher. The color, scene-adaptive HDR display system is based on a high-rate (15 kHz) DMD projector using a high-speed RGB LED illuminator, each color with independent 16 bit intensity control for each binary DMD frame. The critical input to the intensity matching algorithm is the output of an array of high sensitivity light sensors. This paper discusses the implementation of the system and reports performance via still and video demonstrations under a variety of lighting conditions.

We describe an augmented reality, optical see-through display based on a DMD chip with an extremely fast (16 kHz) binary update rate. We combine the techniques of post-rendering 2-D offsets and just-in-time tracking updates with a novel modulation technique for turning binary pixels into perceived gray scale. These processing elements, implemented in an FPGA, are physically mounted along with the optical display elements in a head tracked rig through which users view synthetic imagery superimposed on their real environment. The combination of mechanical tracking at near-zero latency with reconfigurable display processing has given us a measured average of 80 µs of end-to-end latency (from head motion to change in photons from the display) and also a versatile test platform for extremely-low-latency display systems. We have used it to examine the trade-offs between image quality and cost (i.e. power and logical complexity) and have found that quality can be maintained with a fairly simple display modulation scheme.

We present initial results from a new image generation approach for low-latency displays such as those needed in head-worn AR devices. Avoiding the usual video interfaces, such as HDMI, we favor direct control of the internal display technology. We illustrate our new approach with a bench-top optical see-through AR proof-of-concept prototype that uses a Digital Light Processing (DLPTM) projector whose Digital Micromirror Device (DMD) imaging chip is directly controlled by a computer, similar to the way random access memory is controlled. We show that a perceptually-continuous-tone dynamic gray-scale image can be efficiently composed from a very rapid succession of binary (partial) images, each calculated from the continuous-tone image generated with the most recent tracking data. As the DMD projects only a binary image at any moment, it cannot instantly display this latest continuous-tone image, and conventional decomposition of a continuous-tone image into binary time-division-multiplexed values would induce just the latency we seek to avoid. Instead, our approach maintains an estimate of the image the user currently perceives, and at every opportunity allowed by the control circuitry, sets each binary DMD pixel to the value that will reduce the difference between that user-perceived image and the newly generated image from the latest tracking data. The resulting displayed binary image is “neither here nor there,” but always approaches the moving target that is the constantly changing desired image, even when that image changes every 50μs. We compare our experimental results with imagery from a conventional DLP projector with similar internal speed, and demonstrate that AR overlays on a moving object are more effective with this kind of low-latency display device than with displays of similar speed that use a conventional video interface.

We introduce a general technique for blending imagery from multiple projectors on a tracked, moving, non-planar object. Our technique continuously computes visibility of pixels over the surfaces of the object and dynamically computes the per-pixel weights for each projector. This approach supports smooth transitions between areas of the object illuminated by different number of projectors, down to the illumination contribution of individual pixels within each polygon. To achieve real-time performance, we take advantage of graphics hardware, implementing much of the technique with a custom dynamic blending shader program within the GPU associated with each projector. We demonstrate the technique with some tracked objects being illuminated by three projectors.

Applications such as telepresence and training involve the display of real or synthetic humans to multiple viewers. When attempting to render the humans with conventional displays, non-verbal cues such as head pose, gaze direction, body posture, and facial expression are difficult to convey correctly to all viewers. In addition, a framed image of a human conveys only a limited physical sense of presence - primarily through the display's location. While progress continues on articulated robots that mimic humans, the focus has been on the motion and behavior of the robots. We introduce a new approach for robotic avatars of real people: the use of cameras and projectors to capture and map the dynamic motion and appearance of a real person onto a humanoid animatronic model. We call these devices Animatronic Shader Lamps Avatars (SLA).We present a proof-of-concept prototype comprised of a camera, a tracking system, a digital projector, and a life-sized styrofoam head mounted on a pan-tilt unit. The system captures imagery of a moving, talking user and maps the appearance and motion onto the animatronic SLA, delivering a dynamic, real-time representation of the user to multiple viewers.

BACKGROUND: Three-dimensional (3-D) visualization of multimodality neuroimaging data provides a powerful technique for viewing the relationship between structure and function. A number of applications are available that include some aspect of 3-D visualization, including both free and commercial products. These applications range from highly specific programs for a single modality, to general purpose toolkits that include many image processing functions in addition to visualization. However, few if any of these combine both stand-alone and remote multi-modality visualization in an open source, portable and extensible tool that is easy to install and use, yet can be included as a component of a larger information system. RESULTS: We have developed a new open source multimodality 3-D visualization application, called MindSeer, that has these features: integrated and interactive 3-D volume and surface visualization, Java and Java3D for true cross-platform portability, one-click installation and startup, integrated data management to help organize large studies, extensibility through plugins, transparent remote visualization, and the ability to be integrated into larger information management systems. We describe the design and implementation of the system, as well as several case studies that demonstrate its utility. These case studies are available as tutorials or demos on the associated website: http://sig.biostr.washington.edu/projects/MindSeer. CONCLUSION: MindSeer provides a powerful visualization tool for multimodality neuroimaging data. Its architecture and unique features also allow it to be extended into other visualization domains within biomedicine.